A5025332418- Orthopedic Infections and Treatments
- Total Knee Arthroplasty Outcomes
- Orthopaedic implants and arthroplasty
- Evolution and Genetic Dynamics
- Malaria Research and Control
- COVID-19 diagnosis using AI
- COVID-19 Clinical Research Studies
- Vector-borne infectious diseases
- Colorectal Cancer Surgical Treatments
- Machine Learning and Data Classification
- SARS-CoV-2 and COVID-19 Research
- Alzheimer's disease research and treatments
- Colorectal Cancer Screening and Detection
- Memory and Neural Mechanisms
- Machine Learning and Algorithms
- Dementia and Cognitive Impairment Research
- Radiomics and Machine Learning in Medical Imaging
- Complement system in diseases
- COVID-19 and healthcare impacts
- Imbalanced Data Classification Techniques
University of Massachusetts Chan Medical School
2023-2025
Pfizer (United States)
2024
Agency for Healthcare Research and Quality
2024
Patient-Centered Outcomes Research Institute
2024
Zimmer Biomet (Netherlands)
2024
Smith & Nephew (United Kingdom)
2024
Smith & Nephew (United States)
2024
Exactech (France)
2024
Zimmer Biomet (United States)
2024
Smith & Nephew (Switzerland)
2024
The progressive nature of Alzheimer's disease (AD) highlights the importance predicting lifetime risk and updating assessments as new data emerge. This study aimed to develop a dynamic model using longitudinal cognitive for updated predictions. used from Religious Orders Study Rush Memory Aging Project (ROSMAP) prediction based on five domains, annually over 10 years. models 2384 participants showed improved area under curve (AUC) time, rising 0.578 at baseline 0.765 with years data. AD...
In malaria, individuals are often infected with different parasite strains. The complexity of infection (COI) is defined as the number genetically distinct strains in an individual. Changes mean COI a population have been shown to be informative changes transmission intensity probabilistic likelihood and Bayesian models now developed estimate COI. However, rapid, direct measures based on heterozygosity or FwS do not properly represent this work, we present two new methods that use easily...
Background The novel coronavirus SARS-CoV-2 and its associated disease, COVID-19, have caused worldwide disruption, leading countries to take drastic measures address the progression of disease. As continues spread, hospitals are struggling allocate resources patients who most at risk. In this context, it has become important develop models that can accurately predict severity infection hospitalized help guide triage, planning, resource allocation. Objective aim study was accurate mortality...
Current state-of-the-art decision tree algorithms, such as Classification and Regression Trees (CART), build the using a recursive approach based on greedy heuristic. We study benefits of an optimal approach, which creates entire at once Mixed Integer Optimization (MIO). While problems are known to be hard solve for large instances, we leverage modern solver techniques that able obtain near-optimal solutions in reasonable amount time. The methodology is handle both single-feature splits,...
Background Complex machine learning (ML) models have revolutionized predictions in clinical care. However, for laparoscopic colectomy (LC), prediction of morbidity by ML has not been adequately analyzed nor compared against traditional logistic regression (LR) models. Methods All LC patients, between 2017 and 2019, the National Surgical Quality Improvement Program (NSQIP) were identified. A composite outcome 17 variables defined any post-operative morbidity. Seven most common complications...
The effect of mental health on patient-reported outcome measures is not fully understood in total joint arthroplasty (TJA). Thus, we investigated the relationship between diagnoses (MHDs) and Minimal Clinically Important Difference for Improvement (MCID-I) Worsening (MCID-W) primary TJA revision (rTJA).
<sec> <title>BACKGROUND</title> The novel coronavirus SARS-CoV-2 and its associated disease, COVID-19, have caused worldwide disruption, leading countries to take drastic measures address the progression of disease. As continues spread, hospitals are struggling allocate resources patients who most at risk. In this context, it has become important develop models that can accurately predict severity infection hospitalized help guide triage, planning, resource allocation. </sec>...
Abstract In malaria, individuals are often infected with different parasite strains; the complexity of infection (COI) is defined as number genetically distinct strains in an individual. Changes mean COI a population have been shown to be informative changes transmission intensity probabilistic likelihood and Bayesian models now developed estimate COI. However, rapid, direct measures based on heterozygosity or FwS do not properly represent this work, we present two new methods that use...